Sharing a 'RAM' stack between human and agent to keep long revision work on track

alfcnz · x · 2026-11-18

alfcnz describes sharing a stack between himself and his agent: the set goal sits at the bottom, revision tasks are pushed on top, so detours still converge back to the goal. The screenshot shows a concrete working stack (section revisions, pending decisions, parked items). He notes the more he uses this, the more he builds friction-free custom tooling.

Related event: Dev Shares Stack-Based Shared RAM Workflow for Human-Agent Collaboration(2 posts)→

Original post →

More from coding & agent

coding & agent channel →